StarZero All shows Try the podcast clipper →

Albert Gu

Cofounder, Cartesia · 1 appearance on the record.

computed by AI from the episodes · how this works → · full disclaimer →

Albert Gu is a cofounder of Cartesia, a company developing real-time intelligence models for devices. He previously co-invented State Space Models while completing his PhD at the Stanford AI Lab.

8statements → 4claims → 4claims resolved → 100%fully supported → 3.88/5average certainty → 2/5average debate potential → 1said about them ↓

4 supported 0 partly supported 0 contradicted how the 4 claims stand · each chip opens the sources

4 assertions · 1 opinion · 3 insights · every statement was checked. The predictions and assertions are the 4 claims: statements the public record can support or contradict. 4 are resolved. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Albert argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

Their most notable supported claim

Assertion Supported
Gu: Optimal hybrid models use a 10:1 ratio of SSM to attention
“People have found that the optimal ratio tends to be mostly SSM layers with a little bit of attention. So maybe a ratio of like 10 to one, I know of at least Probably like five groups that have independently verified that this is kind of the optimal ratio of t…”
Albert Gu Jun 27, 2024 ▶ 11:30 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu

How they sound: not measured why? →

We measure speaking style by listening to the audio itself, and a fair number needs at least 2,000 words from one person on tape we have measured. There is too little of Albert Gu on measured tape to publish a rate. This says nothing about how they speak.

Everything Albert Gu said on No Priors that made the record, most notable first. Filter by type, assessment or year in the ledger →

Opinion
Gu: Transformers struggle significantly on raw pixel or audio waveform data
“People think that like you can throw a transformer at like anything and it just works. Actually it doesn't really like if you try to throw it at like the raw pixel level or the raw sample level and in audio waveforms I think it doesn't work nearly as well.”
Albert Gu Jun 27, 2024 ▶ 8:16 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Insight
Gu: High-quality speech synthesis requires multimodal foundation models
“And so actually to really get, like, perfect even just TTS or, like, speech-to-speech you actually really need to have, like, a model that has, More understanding, like at least of the language, but kind of like, it's not really an isolated component anymore. …”
Albert Gu Jun 27, 2024 ▶ 24:27 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Assertion Supported
Gu: Optimal hybrid models use a 10:1 ratio of SSM to attention
“People have found that the optimal ratio tends to be mostly SSM layers with a little bit of attention. So maybe a ratio of like 10 to one, I know of at least Probably like five groups that have independently verified that this is kind of the optimal ratio of t…”
Albert Gu Jun 27, 2024 ▶ 11:30 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Assertion Supported
Gu: Mamba successfully applied state-space models to language modeling
“Recently proposed a model called Mamba which was kind of brought these to language modeling and showed really good results there.”
Albert Gu Jun 27, 2024 ▶ 2:24 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Insight
Gu: State Space Models can be applied to almost all data types
“So it really can be applied to pretty much everything. So just like kind of Transformers, these are applied to everything. So can these sort of models over the course of research over a few years, we kind of realized that there are different advantages for dif…”
Albert Gu Jun 27, 2024 ▶ 6:51 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Insight
Gu: Aesthetic elegance was the primary driver behind inventing State Space Models
“People ask me, like, how do I treat my research problems, and my, I can't explain. My answer is just aesthetic. It's just like, there's something that I find elegant, and we're aesthetically pleasing about things, and to me, that's almost the most important th…”
Albert Gu Jun 27, 2024 ▶ 29:30 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Assertion Supported
Gu: Early SSMs excelled at raw signals but lagged Transformers on text
“The first types of models we were looking at were really good actually at modeling kind of these raw waveforms raw pixels, things like that, but not as good at modeling text, and transformers are way better there.”
Albert Gu Jun 27, 2024 ▶ 7:49 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Assertion Supported
Gu: Researchers are applying Mamba-based foundation models to DNA sequences
“So I actually just heard from some collaborators today that they applied a mama based model on DNA modeling. They're basically bringing this idea of foundation models To DNA, which is kind of this new idea.”
Albert Gu Jun 27, 2024 ▶ 12:02 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu

The other half of the tape: Albert Gu's own voice is left out of every number here. Other people bring the name up 1 time in 1 episode on No Priors. every mention, with the transcript →

Who brings them up most Sarah Guo 1

Every mention by year

tap a year for its mentions
0011112025episodesmentions
0112025episodes it came up in
000.50.5112025episodesmentions per episode
2025 1 mention in 1 episode

Appearances (1)

EpisodeDateSpeaking time
No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu Jun 27, 2024 11m
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 100 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more